buglens
Allows AI to read live QA bug data from Google Sheets, filter assigned bugs by type, fetch screenshot links for visual review, and update bug statuses such as In-Progress and Devdone in the correct row.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
π€ The Problem Every Dev Team Has
Your QA team logs bugs in Google Sheets. Smart. Organized. Totally fine.
Then the dev gets pinged.
Here's what actually happens next:
Open the sheet (Tab 1)
Find your assigned bug (scroll, scroll, find the row)
See a Snipboard screenshot link β click it (Tab 2)
Look at the image. Describe it mentally.
Switch back to your code (Tab 3 β or VSCode β or wherever)
Try to fix something you're now half-remembering
Go back to the sheet (Tab 1, again)
Manually type
Devdoneβ or mis-typeDevDoneand break the dropdown
That's 6+ context switches. Per bug. Every single time.
20 bugs a day? You just spent your morning on tab gymnastics.
And the worst part? Your AI assistant never saw the screenshot. You're out here describing UI bugs in plain text like it's 2019.
Related MCP server: io.github.yousefoghouneim-collab/lazyas
π‘ There Is a Better Way
buglens is an MCP server that plugs directly into your editor and closes the entire loop β automatically.
Pull the bug β AI sees the screenshot β Fix the code β Devdone auto β Done β
Your AI reads the sheet live (not a CSV export β live), fetches the Snipboard link, actually sees the visual bug, fixes your code, and marks it Devdone. You never left your editor. You never opened a tab. You never typed a status.
π― How It Works
Step | What Happens | Under the Hood |
1. Live Sheet | AI pulls your open bugs by assignee |
|
2. Vision | AI fetches the Snipboard link and SEES the screenshot |
|
3. Fix | AI understands the visual bug and patches the code | Certificates, Dashboard, Student modules |
4. Devdone | AI writes status back to the exact row |
|
π³ Project Structure
π
__init__.pyπ
server.pyβ Main MCP server containing 8 registered tools
π
GEMINI.mdβ Gemini agent specific configurationsπ
CLAUDE.mdβ Claude agent specific configurationsπ
AGENTS.mdβ General cross-agent context metricsπ
VIBE.mdβ Guidelines for autonomous vibe coding sessionsπ
DEV.mdβ Developer workspace log book
π
pyproject.tomlβ Project metadata and package dependenciesπ«
.gitignoreβ Ignore specs for builds, credentials, and virtual envsπ
README.mdβ This roadmap documentation
Installation
1. Create venv
python3 -m venv venv source venv/bin/activate
2. Install from GitHub
pip install git+https://github.com/iambilalshahid/buglens.git
3. Or for local dev
git clone https://github.com/iambilalshahid/buglens.git cd buglens pip install -e .
[Jump to Gemini Installation](./AGENTS/GEMINI.md)
</details>
<details>
<summary><b>Clone for local dev / contribution</b></summary>
```bash
git clone https://github.com/iambilalshahid/qa-sheet-mcp.git
cd qa-sheet-mcp
python3 -m venv venv
source venv/bin/activate
pip install -e .βοΈ Configuration
Add this block to your mcp.json β works with Cursor, Claude Desktop, and Antigravity.
{
"mcpServers": {
"qa-sheet": {
"command": "python",
"args": ["-m", "qa_sheet_mcp.server"],
"env": {
"SHEET_ID": "your-sheet-id-here",
"WORKSHEET_NAME": "Admin bug report",
"GOOGLE_CREDS_PATH": "./credentials.json",
"QA_ASSIGN_TO": "Bilal",
"QA_PROBLEM_TYPE": "FE"
}
}
}
}Variable | Description |
| From URL |
| Your sheet tab name β e.g. |
| Path to your Service Account |
| Your name exactly as it appears in the sheet: |
| Filter by type: |
π Status Workflow
Every transition is validated. No more typos silently breaking your dropdown.
stateDiagram-v2
[*] --> Open
Open --> InProgress
InProgress --> Devdone
InProgress --> ServerDone
Devdone --> QA
ServerDone --> QA
QA --> Verified
QA --> ReOpen
ReOpen --> InProgress
Verified --> [*]Valid values: Open Β· In-Progress Β· Devdone Β· QA Β· Re-Open Β· Verified Β· Discussion Β· Hold Β· Server Done
π οΈ The 7 Tools
Tool | What it does |
| Pull your open FE bugs live from the sheet (with |
| Fetch Snipboard URL β base64 β AI sees the bug visually |
| Flip status: |
| Flip status: β |
| Valid dropdown values + full workflow reference |
| What you fixed today β reads from |
| Sheet debug info when things go sideways |
π€ Contribute
Open source, solo-built, PRs welcome β especially for:
New tool ideas (comment on a bug row? bulk update?)
More integrations: Notion, Jira, Linear
Better vision prompting strategies
git clone https://github.com/iambilalshahid/qa-sheet-mcp.git
git checkout -b feature/your-idea
git commit -m "Add: your feature"
git push origin feature/your-idea
# β Open a Pull Requestπ€ Author
Bilal Shahid β Solo Dev GitHub: @iambilalshahid
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogβ¦
This server cannot be deployed
Maintenance
Related MCP Connectors
Connect AI assistants to Google Sheets through controlled tools for reading and updating rows.
Connect an AI assistant to your Google Sheets, Drive, Docs, PDFs, BigQuery and Gmail.
Run accessibility, contrast, and design token audits and file QA issues from your AI coding tool.
Give AI coding agents access to your Vynix visual feedback, bug reports, and AI diagnosis.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to debug frontend applications by providing direct access to browser DevTools, React state, DOM inspection, and runtime debugging capabilities. Bridges the gap between AI and complex web applications for autonomous debugging and issue resolution.1MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI coding agents to read point-and-talk review notes with marked screenshots, fix them by number, and report each fix back with proof so nothing is considered done until verified.MIT

Jot MCP Serverofficial
AlicenseAqualityCmaintenanceEnables AI coding agents to inspect user feedback on live web apps, read full reports and recording timelines, update status, and reply in threads so fixes can be checked and confirmed by reporters.5MIT- AlicenseAqualityBmaintenanceEnables coding agents to turn Jira Cloud tickets into ready-to-build briefs, verify local branches against acceptance criteria, and prepare QA handoffs, with optional previewed and audited write-back.1081 npmMIT